A computer-implemented method includes identifying two or more memory locations and referencing, by a memory access request, the two or more memory locations. The memory access request is a single action pursuant to a memory protocol. The computer-implemented method further includes sending the memory access request from one or more processors to a node and fetching, by the node, data content from each of the two or more memory locations. The computer-implemented method further includes packaging, by the node, the data content from each of the two or more memory locations into a memory package, and returning the memory package from the node to the one or more processors. A corresponding computer program product and computer system are also disclosed.
Legal claims defining the scope of protection, as filed with the USPTO.
1. A computer-implemented method comprising: identifying two or more memory locations, wherein said two or more memory locations are not contiguous; referencing, by a memory access request, said two or more memory locations; sending said memory access request from one or more processors to a node, said memory access request comprising a single action pursuant to a memory protocol; fetching, by said node, data content from each of said two or more memory locations, wherein said node is of at least one type selected from the group consisting of: one or more additional processors, a memory controller, and a cache controller; packaging, by said node, said data content from each of said two or more memory locations into a memory package; returning said memory package from said node to said one or more processors; initiating a transaction in a transactional memory environment, wherein said two or more memory locations are used in said transaction; and wherein referencing, by the memory access request, said two or more memory locations comprises: identifying numerical addresses for said two or more memory locations; identifying, in said numerical addresses, shared high order bits; and compressing said two or more memory locations based on said shared high order bits.
2. The computer-implemented method of claim 1 , wherein: said one or more processors communicate with said node via a system bus; said one or more processors are in electronic communication with at least one of a memory queue register or an other processor cache; and referencing, by a memory access request, said two or more memory locations comprises: storing said two or more memory locations in said memory queue register or said other processor cache; and placing each of said two or more memory locations from said memory queue register or said other processor cache onto said system bus.
3. The computer-implemented method of claim 2 , wherein placing each of said two or more memory locations from said memory queue register or said other processor cache onto said system bus are done in parallel in a single cycle of said one or more processors.
4. The computer-implemented method of claim 2 , wherein placing each of said two or more memory locations from said memory queue register onto said system bus is done serially in consecutive cycles of said one or more processors.
5. The computer-implemented method of claim 1 , wherein referencing, by a memory access request, said two or more memory locations comprises: identifying a reference memory location; and storing, at said reference memory location, said two or more memory locations.
6. The computer-implemented method of claim 1 , wherein said two or more memory locations are addresses in physical memory.
Cooperative Patent Classification codes for this invention. Click any code to explore related patents in that topic.
May 20, 2016
January 3, 2017
Browse 5M+ US patents with plain-English claim translations and AI-generated analysis.